Research On License Plate Location And Character Segment In Vehicle License Plate Recognition System

With the development of information technology and intelligence technology, the information and intelligent of traffic management is the trend.License Plate Recognition system (LPR) is the core of Intelligent Traffic System (ITS). It is very important in modern traffic management systems. In recent years, the study on the critical techniques for LPR has already become an important research field of scientific circles. In this paper we discuss the three parts of License Plate Recognition Systems:image pre-process, license plate location and character segmentation, and make a deep research on some important and key technology.In this paper, we first summarize the domestic and foreign development of the current license plate recognition system, and we study some representative license plate recognition technology, and we study some representative license plate recognition technology, and combined with characteristics of the Chinese license plates, the algorithm of the key part of license plate recognition achieved by MATLAB software.License plate location is a critical step in the license plate recognition system; its result will directly affect the accuracy of character segmentation and recognition. Base on the analysis and summarizes of several algorithms in the license plate location, it used the method that based on color feature and projection. The algorithm has two locations on the collected license plate. It mainly use the color characteristics of the license plate in the first location, first, we need to transform the plate image color model space, that is RGB turn into HIS. Because of the blue color'H is about 240°, and the value of saturation S is larger than other color, so we can use H and S to filter out the blue part in plate images, so it is the first plate location. Before the precise location is some image processing methods, such as the removal of isolated points, shift differential scanning and edge detection. At last, we use horizontal projection and vertical projection to complete the second precise location.Image processing technology also plays an important role in the license plate recognition system. In License plate location and character segmentation, we use some important image processing methods, such as edge detection, image enhancement, image binarization, etc.These image processing methods can greatly improve the accuracy of license plate location and character segmentationCharacter segmentation is an important part of nexus in the license plate recognition system. First of all, this article use a series of image processing operations that include gray stretch, image filtering and sharpening, binarization, tilt correction, remove the frame, then the paper give some traditional introduction of license plate character segmentation algorithm, then we proposed algorithm that base on rotating projection and prior knowledge.The results of experiments show that the method used in this paper can achieve a better effect in license plate location and character segmentation, the algorithm has a robust and timeliness.